Reasoning & math
AuraScore 89/100

Overall Equipment Effectiveness Loss Factor Assessment

Calculate and dissect availability, performance, and quality metrics into an actionable equipment loss diagnostic report.

Use this template when evaluating complex manufacturing downtime, minor stops, and scrap counts to diagnose true mechanical efficiency. It decomposes raw shift metrics into standard mathematical loss categories to guide preventative maintenance interventions.

Template

Role: Senior Manufacturing Operations Metrologist and Reliability Analyst with twenty years of experience in discrete production optimization.

Context

  • Manufacturing facility: {{plant_facility}}
  • Target production asset: {{production_line}}
  • Planned operational window: {{planned_operating_time}}
  • Unplanned stoppage logs: {{actual_downtime_minutes}}
  • Standard operating rate: {{ideal_cycle_time}}
  • Gross production output: {{total_units_produced}}
  • Rejected part count: {{defective_units_count}}

Task

Generate a structured quantitative report breaking down Overall Equipment Effectiveness (OEE) into its three underlying mathematical components (Availability, Performance, and Quality), isolating the primary root-loss drivers across the target production shift.

Method

  1. Calculate total Operating Time by subtracting {{actual_downtime_minutes}} from {{planned_operating_time}}.
  2. Compute the Availability percentage as Operating Time divided by {{planned_operating_time}}.
  3. Compute Net Operating Time using {{ideal_cycle_time}} multiplied by {{total_units_produced}}.
  4. Determine Performance percentage by dividing Net Operating Time by Operating Time, noting speed loss variance.
  5. Compute Quality percentage by dividing good units ({{total_units_produced}} minus {{defective_units_count}}) by {{total_units_produced}}.
  6. Multiply Availability, Performance, and Quality to establish final composite OEE.
  7. Categorize downtime into the Six Big Losses (breakdowns, setup adjustments, small stops, reduced speed, process defects, startup reject).
  8. Prioritize the largest numerical variance factor and formulate specific engineering corrective actions.

Constraints

  • All mathematical equations MUST be explicitly shown with substituted numerical values.
  • Percentages MUST be rounded precisely to two decimal places.
  • MUST NOT introduce speculative external downtime reasons not supported by the input telemetry.
  • Total word count must remain between 400 and 700 words.

Output format

  1. Executive Scorecard (Table of Availability, Performance, Quality, and Composite OEE)
  2. Step-by-Step Mathematical Derivations (Numbered breakdown of each computation)
  3. Six Big Losses Variance Decomposition (Categorized breakdown of lost operating minutes)
  4. Reliability Engineering Next Steps (3 targeted, prioritized remediation actions)

Self-review

  • Confirm composite OEE matches the product of individual rate percentages.
  • Verify all numerical figures align exactly with {{planned_operating_time}} and associated inputs.
  • Ensure no mathematical steps are skipped or implied.
AuraScore breakdown
89/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification14/14 · Strong

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

research-analysis
research-reasoning-math
manufacturing-industrial
oee
manufacturing
reliability